Skip to main content
Workspaces give your agent persistent file storage. Two patterns cover almost every use case:
  1. You upload a file → agent reads it
  2. Agent creates a file → you download it

​
Upload a file

from browser_use_sdk.v3 import AsyncBrowserUse

client = AsyncBrowserUse()
workspace = await client.workspaces.create(name="my-workspace")

# Upload
await client.workspaces.upload(workspace.id, "people.csv")

# Agent can now read it
result = await client.run(
    "Read people.csv and tell me who works at Google",
    workspace_id=workspace.id,
)
print(result.output)
You can upload multiple files at once: 
await client.workspaces.upload(workspace.id, "data.csv", "config.json", "image.png")

​
Download files

from browser_use_sdk.v3 import AsyncBrowserUse

client = AsyncBrowserUse()
workspace = await client.workspaces.create(name="my-workspace")

# Agent creates a file
result = await client.run(
    "Go to Hacker News and save the top 3 posts as posts.json",
    workspace_id=workspace.id,
)

# Download a single file
await client.workspaces.download(workspace.id, "posts.json", to="./posts.json")

# Or download everything
paths = await client.workspaces.download_all(workspace.id, to="./output")
for p in paths:
    print(f"Downloaded: {p}")

​
Manage workspaces

workspace = await client.workspaces.get(workspace_id)
updated = await client.workspaces.update(workspace_id, name="renamed")
response = await client.workspaces.list()
for w in response.items:
    print(w.id, w.name)
await client.workspaces.delete(workspace_id)

​
Organize with prefixes

Use prefix to organize files into directories within a workspace: 
# Upload into a subdirectory
await client.workspaces.upload(workspace.id, "report.pdf", prefix="reports/")

# List files in a subdirectory
files = await client.workspaces.files(workspace.id, prefix="reports/")
for f in files.files:
    print(f.path, f.size)

# Download only files from a subdirectory
await client.workspaces.download_all(workspace.id, to="./output", prefix="reports/")

​
List and delete files

# List all files
files = await client.workspaces.files(workspace.id)
for f in files.files:
    print(f.path, f.size)

# Delete a single file
await client.workspaces.delete_file(workspace.id, path="old-report.pdf")

# Check workspace storage usage
size = await client.workspaces.size(workspace.id)
print(f"Used: {size.used_bytes} bytes")

​
Cloud dashboard

You can also manage workspaces from cloud.browser-use.com/settings.
Deleting a workspace permanently removes all its files. This cannot be undone.